Deep learning for knowledge discovery

1.

Subject title

Deep learning for knowledge discovery

Откривање знаење со длабоко учење

2.

Code

F23L3S106

3.

Study program

Примена на информациски технологии, Софтверско инженерство и информациски системи, Компјутерски науки, Компјутерско инженерство, Интернет, мрежи и безбедност, Информатичка едукација, Software engineering and information systems, Примена на информациски технологии, Софтверско инженерство и информациски системи, Компјутерски науки, Компјутерско инженерство, Интернет, мрежи и безбедност, Software engineering and information systems, Стручни студии за програмирање, Стручни студии за програмирање, Bioinformatics,

4.

Organizer of the study program (unit, institute, department, division)

Faculty of Information Sciences and Computer Engineering

5.

Study cycle (first, second, third)

Прв циклус

6.

Academic year / semester

4 / Летен

7. Number of ECTS credits

6.0

8.

Instructor

проф. д-р Кире Триводалиев проф. д-р Слободан Калајџиски проф. д-р Соња Гиевска

9.

Prerequisites for enrollment

Вештачка интелигенција или Вовед во науката за податоци или Машинско учење

10.

Subject goals and competencies:

After completing the course, the student will be able to choose appropriate techniques for discovering and extracting knowledge from different types of data. The student will possess knowledge of advanced deep learning architectures with applications in recommendation systems, graph-structured data analysis, and multimodal data fusion.

11.

Subject content:

1. Introduction to the topics covered by the subject. Advanced methods of machine learning and areas of their application. 2. Graph-structured data. Analysis of static and dynamic properties of graphs. 3. Application of graph neural networks to graph analysis 4. Representation of nodes and links in graphs 5. Extracting knowledge from social networks: Predicting relationships. Classification and annotation of nodes. 6. Application of graph-neural networks for recommender systems 7. Approaches based on deep learning and supervised learning 8. Generative adversarial networks 9. Application of GAN in machine vision and natural language processing 10. Multimodal fusion 11. Deep neural networks for multimodal fusion with application areas 12. Case studies of the application of boosted learning, graph neural networks and generative adversarial networks

12.

Learning methods:

Предавања поддржани со презентации преку слајдови, интерактивни предавања, вежби (користење на опрема и софтверски пакети), тимска работа, пример случаи, поканети гости предавачи, самостојна изработка и одбрана на проектна задача и семинарска работа, учење во електронско опкружување (форуми, консултации).

13.

Total available time fund

6.0 ECTS x 30 hours = 180 hours

14.

Time distribution

30 + 45 + 15 + 15 + 75 = 180 hours

15.

Forms of teaching activities

15.1.

Lectures - theoretical teaching

30 hours

15.2.

Exercises (laboratory, classroom), seminars, team work

45 hours

16.

Other forms of activities

16.1.

Project tasks

15 hours

16.2.

Independent tasks

15 hours

16.3.

Homework

75 hours

17.

Grading method

17.1.

Tests

points

17.2.

Seminar work / project (presentation: written and oral)

15 points

17.3.

Activities and learning

10 points

17.4.

Final exam

10 points

18.

Grading criteria (points / grade)

up to 50 points

5 (five) (F)

from 51 to 60 points

6 (six) (E)

from 61 to 70 points

7 (seven) (D)

from 71 to 80 points

8 (eight) (C)

from 81 to 90 points

9 (nine) (B)

from 91 to 100 points

10 (ten) (A)

19.

Condition for signature and taking final exam

освоени 50% од предвидените поени на индивидуалните задачи

20.

Language of instruction

македонски и англиски

21.

Quality assurance method

механизам на интерна евалуација и анкети

22.

Literature

22.1.

Mandatory literature

22.2.

Additional literature